rbbt-text 1.3.10 → 1.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2f10312d9b6598ddc9b6fa98b38909afdd575b33a497ae1ff3f17c7a9c6e37bf
-  data.tar.gz: f79c61c7e34dd113a2c5002342c0c2df92a4a28c770394bf2c456a34a2730cc7
+  metadata.gz: 581a8bf4e03fad79e2650c65ac6c445d83f89a1d237114c91e8ba37b11c1c4f4
+  data.tar.gz: 58f2fb21eee7ac37ca30a771609f6b0c394a2b646690fbcd59b0d623261e0522
 SHA512:
-  metadata.gz: a9fb4dc49c538a58a8aa04e81947df212668c5ef9097434fa7d3eff54dd17a8657f581451b64e6b247cb64428436823a305dd64ae6a5fed2126b92285c02ad81
-  data.tar.gz: 0d31423660cd232102aa2b9914dab61ff929cf02a37b5094bd58481cac733c167d0e4fcdb4b3025e41a4775bd8033566ed3f402f66c317b3955406d1a3d3eb6f
+  metadata.gz: 646340e7dc850bbe4232f30e947f68b8801b51b6d3e0ded92f378534459993cf08c21885685fe4e11a171026f0b0f09d331fdbdc70d97e81579f0ad53f886ee2
+  data.tar.gz: 68b0095f69e08562a22763201c8175e5f6e10d9106118f9dd3b2920a0ae63111f6296dd03b66fd1ab6a5672898a8c4e87d2ca5190671e60ad44b9ea0e6dab78c

data/lib/rbbt/bow/misc.rb

@@ -37,7 +37,7 @@ $greek.each{|l,s| $inverse_greek[s] = l }
 
 class String
   CONSONANTS = []
-  if File.exists? File.join(Rbbt.datadir, 'wordlists/consonants')
+  if File.exist? File.join(Rbbt.datadir, 'wordlists/consonants')
     Object::Open.read(File.join(Rbbt.datadir, 'wordlists/consonants')).each_line{|l| CONSONANTS << l.chomp}
   end
 

data/lib/rbbt/document/corpus/pubmed.rb

@@ -20,13 +20,25 @@ module Document::Corpus
                  elsif type.to_sym == :title
                    Document.setup(article.title || "", PUBMED_NAMESPACE, pmid, type.to_sym, self)
                  elsif type.to_sym == :title_and_abstract
-                   Document.setup((article.title || "") + "\n\n" + (article.abstract || ""), PUBMED_NAMESPACE, pmid, type.to_sym, self)
+                   title = article.title
+                   abstract = article.abstract
+
+                   if title.nil? || title == ""
+                     text = article.abstract
+                     text = "" if text.nil?
+                   else
+                     title = title + "." unless title.end_with?(".")
+
+                     text = title + " " + abstract if abstract && ! abstract.empty?
+                   end
+
+                   Document.setup(text, PUBMED_NAMESPACE, pmid, type.to_sym, self)
                  else
                    raise "No FullText available for #{ pmid }" if article.full_text.nil?
                    Document.setup(article.full_text, PUBMED_NAMESPACE, pmid, :fulltext, self, :corpus => self)
                  end
       Log.debug "Loading pmid #{pmid}"
-      add_document(document)
+      add_document(document) if document
       document
     end
 

data/lib/rbbt/ner/g_norm_plus.rb

@@ -66,7 +66,7 @@ EOF
         end
 
         Open.write('config', CONFIG)
-        mem = Rbbt::Config.get(:java_mem, :GNormPlus, :g_norm_plus, :gnormplus, :gnp, :default => "2G")
+        mem = Rbbt::Config.get(:java_mem, :GNormPlus, :g_norm_plus, :gnormplus, :gnp, :default => "8G")
         CMD.cmd_log("java -Xmx#{mem} -Xms#{mem}  -jar '#{Rbbt.software.opt.GNormPlus.produce.find}/GNormPlus.jar' 'input' 'output' 'config'")
 
         if texts.respond_to? :key_field

data/share/install/software/OpenNLP

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 name='OpenNLP'
-url="http://apache.rediris.es/opennlp/opennlp-1.9.4/apache-opennlp-1.9.4-bin.tar.gz"
+url="http://apache.rediris.es/opennlp/opennlp-2.3.0/apache-opennlp-2.3.0-bin.tar.gz"
 
 install_src $name $url
 (cd $OPT_DIR/jars; ln -s $OPT_DIR/$name/lib/*.jar .)

data/test/rbbt/ner/test_g_norm_plus.rb

@@ -3,7 +3,7 @@ require 'rbbt/ner/g_norm_plus'
 
 Log.severity = 0
 class TestGNormPlus < Test::Unit::TestCase
-  def test_match
+  def _test_match
     text =<<-EOF
 
 Introduction
@@ -12,7 +12,7 @@ We found that TP53 is regulated by MDM2 in Homo
 sapiens
     EOF
 
-    Rbbt::Config.add_entry :java_mem, "2G", :gnp
+    Rbbt::Config.add_entry :java_mem, "16G", :gnp
     mentions = GNormPlus.process({:file => text})
 
     assert_equal 1, mentions.length
@@ -24,7 +24,7 @@ sapiens
 We found that TP53 is regulated by MDM2 in Homo sapiens
     EOF
 
-    Rbbt::Config.add_entry :java_mem, "2G", :gnp
+    Rbbt::Config.add_entry :java_mem, "16G", :gnp
     mentions = GNormPlus.entities({:file => text})
     assert mentions["file"].include?("TP53")
     mentions["file"].each do |mention|

data/test/test_helper.rb

@@ -15,7 +15,11 @@ class Test::Unit::TestCase
 
   def setup
     FileUtils.mkdir_p Rbbt.tmp.test.persistence.find(:user)
-    Persist.cachedir = Rbbt.tmp.test.persistence.find :user
+    begin
+      Persist.cachedir = Rbbt.tmp.test.persistence.find :user
+    rescue
+      Persist.cache_dir = Rbbt.tmp.test.persistence.find :user
+    end
   end
 
   def teardown

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-text
 version: !ruby/object:Gem::Version
-  version: 1.3.10
+  version: 1.4.0
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-02-28 00:00:00.000000000 Z
+date: 2023-12-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -175,45 +175,45 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
+rubygems_version: 3.5.0.dev
 signing_key: 
 specification_version: 4
 summary: Text mining tools for the Ruby Bioinformatics Toolkit (rbbt)
 test_files:
-- test/test_spaCy.rb
-- test/test_helper.rb
-- test/rbbt/bow/test_dictionary.rb
 - test/rbbt/bow/test_bow.rb
+- test/rbbt/bow/test_dictionary.rb
 - test/rbbt/bow/test_misc.rb
-- test/rbbt/segment/test_encoding.rb
-- test/rbbt/segment/test_transformed.rb
-- test/rbbt/segment/test_overlaps.rb
-- test/rbbt/segment/test_named_entity.rb
-- test/rbbt/segment/test_corpus.rb
-- test/rbbt/segment/test_range_index.rb
-- test/rbbt/segment/test_annotation.rb
-- test/rbbt/entity/test_document.rb
 - test/rbbt/document/corpus/test_pubmed.rb
-- test/rbbt/document/test_corpus.rb
 - test/rbbt/document/test_annotation.rb
-- test/rbbt/test_document.rb
-- test/rbbt/ner/test_patterns.rb
+- test/rbbt/document/test_corpus.rb
+- test/rbbt/entity/test_document.rb
 - test/rbbt/ner/rnorm/test_tokens.rb
-- test/rbbt/ner/test_ngram_prefix_dictionary.rb
-- test/rbbt/ner/test_token_trieNER.rb
-- test/rbbt/ner/test_finder.rb
+- test/rbbt/ner/test_NER.rb
+- test/rbbt/ner/test_abner.rb
+- test/rbbt/ner/test_banner.rb
 - test/rbbt/ner/test_brat.rb
-- test/rbbt/ner/test_regexpNER.rb
+- test/rbbt/ner/test_chemical_tagger.rb
+- test/rbbt/ner/test_finder.rb
 - test/rbbt/ner/test_g_norm_plus.rb
-- test/rbbt/ner/test_rnorm.rb
 - test/rbbt/ner/test_linnaeus.rb
-- test/rbbt/ner/test_chemical_tagger.rb
-- test/rbbt/ner/test_NER.rb
-- test/rbbt/ner/test_abner.rb
-- test/rbbt/ner/test_rner.rb
+- test/rbbt/ner/test_ngram_prefix_dictionary.rb
 - test/rbbt/ner/test_oscar4.rb
-- test/rbbt/ner/test_banner.rb
-- test/rbbt/test_segment.rb
+- test/rbbt/ner/test_patterns.rb
+- test/rbbt/ner/test_regexpNER.rb
+- test/rbbt/ner/test_rner.rb
+- test/rbbt/ner/test_rnorm.rb
+- test/rbbt/ner/test_token_trieNER.rb
+- test/rbbt/nlp/genia/test_sentence_splitter.rb
 - test/rbbt/nlp/open_nlp/test_sentence_splitter.rb
 - test/rbbt/nlp/test_nlp.rb
-- test/rbbt/nlp/genia/test_sentence_splitter.rb
+- test/rbbt/segment/test_annotation.rb
+- test/rbbt/segment/test_corpus.rb
+- test/rbbt/segment/test_encoding.rb
+- test/rbbt/segment/test_named_entity.rb
+- test/rbbt/segment/test_overlaps.rb
+- test/rbbt/segment/test_range_index.rb
+- test/rbbt/segment/test_transformed.rb
+- test/rbbt/test_document.rb
+- test/rbbt/test_segment.rb
+- test/test_helper.rb
+- test/test_spaCy.rb